geohotstan dd82b4c913 make onnx runner a class (#8647) ...

* this

* clean up

* more clean ups and improve debug msg

* more correct training toggler

* remove manual training toggling

* change some variable names

* actually just add the training toggle for LIMIT envvar too

* more refinement

* __call__ and OnnxRunner

* fix half pylint, other half is importing from onnx while this file is onnx.py, figure out later

* ahhhh found another mistake

* remove limit from __call__

---------

Co-authored-by: chenyu <chenyu@fastmail.com>

2025-01-20 10:11:05 -08:00

..

conversation_data

Whisper + LLAMA + VITS (#2332)

2023-12-02 15:03:46 -08:00

llm.c

create_schedule([x.lazydata]) -> x.schedule() in tests (#8449)

2024-12-31 03:15:52 +08:00

mlperf

bert BS 72->66 [pr] (#8621)

2025-01-14 18:41:41 -05:00

openpilot

make onnx runner a class (#8647)

2025-01-20 10:11:05 -08:00

other_mnist

beautiful_mnist in torch

2024-07-14 11:09:58 -07:00

rl

more beautiful_cartpole with exposed hparams

2024-01-07 17:41:09 -08:00

sovits_helpers

combine pad2d with pad (#7677)

2024-11-14 17:56:02 +08:00

tinychat

make tinychat local (#7871)

2024-11-24 14:45:48 +08:00

vgg7_helpers

move to new cached fetch (#2493)

2023-11-28 17:36:55 -08:00

webgpu

encapsulate the exported webgpu model (#8203)

2024-12-13 10:55:37 +01:00

__init__.py

failing llama test

2023-03-11 16:28:10 -08:00

beautiful_cartpole.py

tinytqdm.set_description and tinytrange (#5101)

2024-06-22 14:45:06 -04:00

beautiful_cifar.py

Fix mypy examples/beautiful_*.py (#6978)

2024-10-10 11:34:29 -04:00

beautiful_mnist_multigpu.py

Fix mypy examples/beautiful_*.py (#6978)

2024-10-10 11:34:29 -04:00

beautiful_mnist.py

Revert "switch beautiful_mnist to use new optimizer [pr] (#8231)" (#8233)

2024-12-13 19:07:09 -08:00

benchmark_onnx.py

make onnx runner a class (#8647)

2025-01-20 10:11:05 -08:00

coder.py

apply the same fix_bf16 in llama and coder (#3789)

2024-03-17 21:25:24 -04:00

compile_efficientnet.py

Remove WebGL (#8012)

2024-12-03 16:02:53 +01:00

compile_tensorflow.py

make onnx runner a class (#8647)

2025-01-20 10:11:05 -08:00

conversation.py

Fix examples/conversation.py (#8425)

2024-12-26 12:45:19 -05:00

efficientnet.py

remove clang program header (#4422)

2024-05-04 08:38:01 -07:00

flux1_seed0.png

Flux.1 (#6334)

2024-09-24 10:08:04 +08:00

flux1.py

flux set model path in args (#7660)

2024-11-12 22:11:40 -05:00

gpt2.py

really not using numpy in gpt2 example (#7779)

2024-11-18 23:21:16 -05:00

handcode_opt.py

fix handcode_opt bert [pr] (#8509)

2025-01-05 19:14:12 -05:00

hlb_cifar10.py

combine pad2d with pad (#7677)

2024-11-14 17:56:02 +08:00

llama3.py

hotfix: default llama3 is 1B with download_model

2024-12-09 07:23:35 -08:00

llama.py

validate llama quantize output (#7901)

2024-11-25 16:46:23 -05:00

mamba.py

prev speed improvements (#5252)

2024-07-03 09:06:01 -07:00

mask_rcnn.py

change Tensor.stack to method (#4719)

2024-05-24 17:04:19 -04:00

mixtral.py

tinytqdm.set_description and tinytrange (#5101)

2024-06-22 14:45:06 -04:00

mnist_gan.py

tinytqdm.set_description and tinytrange (#5101)

2024-06-22 14:45:06 -04:00

openelm.py

nn.RMSNorm (#5272)

2024-07-02 21:39:01 -04:00

qwq.py

QwQ-32B-Preview support (#7962)

2024-12-04 21:46:37 -05:00

sdv2.py

Stable Diffusion v2 Inference (#5283)

2024-07-03 22:47:10 -04:00

sdxl_seed0.png

default threefry (#6116)

2024-09-25 17:45:13 +08:00

sdxl.py

GlobalCounters.reset() in sdxl step [pr] (#8664)

2025-01-17 21:10:28 -05:00

self_tokenize.py

make self_tokenize output more like a python file (#8411)

2024-12-25 14:16:30 -05:00

serious_mnist.py

combine pad2d with pad (#7677)

2024-11-14 17:56:02 +08:00

simple_conv_bn.py

fix various examples (#4691)

2024-05-22 20:43:21 -04:00

so_vits_svc.py

combine pad2d with pad (#7677)

2024-11-14 17:56:02 +08:00

stable_diffusion_seed0.png

default threefry (#6116)

2024-09-25 17:45:13 +08:00

stable_diffusion.py

Remove wgpu specific checks from stable diffusion example (#7991)

2024-12-02 11:31:14 +01:00

stunning_mnist.py

stunning_mnist [run_process_replay] (#6828)

2024-10-01 15:00:48 +08:00

test_onnx_imagenet.py

fix onnx mobilenetv2-7-quantized.onnx (#8574)

2025-01-13 09:25:06 -08:00

train_efficientnet.py

tinytqdm.set_description and tinytrange (#5101)

2024-06-22 14:45:06 -04:00

train_resnet.py

move things, clean up extra (#2292)

2023-11-13 20:18:40 -08:00

transformer.py

fix onehot and jit in examples/transformer (#3073)

2024-01-10 02:22:41 -05:00

vgg7.py

waifu2x vgg7: testcase, auto-RGBA->RGB, function to grab pretrained models, training "fix" (#2117)

2023-10-19 22:07:15 -07:00

vit.py

move to new cached fetch (#2493)

2023-11-28 17:36:55 -08:00

vits.py

Fix examples/conversation.py (#8425)

2024-12-26 12:45:19 -05:00

whisper.py

enable whisper batch for long sequences (#6458)

2024-09-17 00:42:10 -04:00

yolov3.py

Update yolov3.py (#2680)

2023-12-08 12:59:38 -08:00

yolov8-onnx.py

make onnx runner a class (#8647)

2025-01-20 10:11:05 -08:00

yolov8.py

YoloV8 on WebGPU (#8007)

2024-12-03 15:10:41 +01:00